Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A device for automatically classifying animal behaviors comprising: a study animal type; a vivarium comprising a set of study animals, of the study animal type, in a plurality of cages; a non-transitory first memory comprising a first set of positive video and audio behaviors; a non-transitory second memory comprising a second set of negative video and audio behaviors; at least one ultrasonic audio sensor proximal to an each cage in the plurality of cages; at least one video camera proximal to the each cage in the plurality of cages; wherein at least one ultrasonic sensor and at least one video sensor detect and automatically communicate first communicated behaviors comprising one or more audio and video behaviors, from the at least one cage in the plurality of cages, respectively; a first processor adapted to identify a first selected set of behaviors derived from the first communicated behaviors, wherein each behavior in the first selected set of behaviors is consistent with one or both of at least one behavior in the first set of positive video and audio behaviors; or at least one behavior in the second set of negative video and audio behaviors; a second processor adapted to classify the first selected set of behaviors responsive to at least both of: (a) a least difference between the first selected set of behaviors and the first set of positive video and audio behaviors, and (b) a largest difference between the first selected set of behaviors and the second set of negative video and audio behaviors; wherein the first and second processors are configurable to operate as a same processor; wherein each of the automatically classified animal behaviors by the device is quantified; wherein the at least a subset of the automatically classified animal behaviors comprising classified ultrasonic vocalization is then used as accepted dispositive animal behavior.
This invention relates to an automated system for classifying animal behaviors in a vivarium setting. The system addresses the challenge of efficiently and accurately monitoring and categorizing animal behaviors, particularly in research environments where manual observation is time-consuming and subjective. The device includes a vivarium housing multiple cages containing study animals of a specified type. Each cage is equipped with at least one ultrasonic audio sensor and one video camera to capture audio and video behaviors. These sensors detect and transmit behaviors from the cages to a processing system. The system compares the detected behaviors against predefined sets of positive (desired) and negative (undesired) behaviors stored in separate memory modules. A processor identifies behaviors that match either the positive or negative sets and classifies them based on the smallest difference to positive behaviors and the largest difference to negative behaviors. The processors can be configured to operate as a single unit. The classified behaviors are quantified, and ultrasonic vocalizations are used as definitive evidence of animal behavior. This system automates behavior classification, reducing human bias and improving research efficiency.
2. The device of claim 1 , wherein: the classified ultrasonic vocalizations comprise two or more vocalizations from the Markush group of accent; upward; downward; flat; chevron; U-shaped; and complex.
This invention relates to a device for analyzing and classifying ultrasonic vocalizations, particularly those produced by animals such as bats or rodents. The device addresses the challenge of accurately identifying and categorizing different types of ultrasonic vocalizations, which are often used in communication, navigation, or echolocation. The device includes a system for capturing and processing these vocalizations, distinguishing them based on their acoustic characteristics. The classified ultrasonic vocalizations include two or more distinct patterns from a defined group: accent, upward, downward, flat, chevron, U-shaped, and complex. These patterns represent different shapes or modulations in the frequency or amplitude of the vocalizations. The device may use signal processing techniques, such as spectral analysis or machine learning, to detect and classify these patterns. The classification helps in understanding animal behavior, studying communication systems, or developing bioacoustic monitoring tools. The device may also include a display or output interface to present the classified vocalizations for further analysis.
3. The device of claim 1 , wherein: the classified ultrasonic vocalizations comprise two or more vocalizations from the Markush group of shape of pitch v. time; intensity; number of times a vocalization occurs within a predetermined time window; change in pitch measured as Hz/time; and simultaneous vocalizations below 25 KHz.
This invention relates to a device for analyzing ultrasonic vocalizations, particularly in animal communication or monitoring systems. The device classifies vocalizations based on specific acoustic features to distinguish between different types of sounds. The classified vocalizations include two or more distinct characteristics from a defined group: the shape of pitch over time, intensity, the frequency of occurrence within a set time window, pitch change rate in Hz per unit time, and simultaneous vocalizations below 25 KHz. These features enable the device to identify and categorize complex ultrasonic sounds, improving accuracy in detecting and interpreting animal vocalizations. The system likely processes raw ultrasonic signals, extracts these key parameters, and applies classification algorithms to differentiate between vocalization types. This approach enhances monitoring applications in wildlife research, veterinary diagnostics, or bioacoustic studies by providing detailed acoustic analysis beyond simple frequency detection. The device may integrate with sensors, signal processors, and machine learning models to automate vocalization classification in real-time or batch processing scenarios. The focus on multiple acoustic dimensions ensures robust discrimination between vocalizations, addressing challenges in noisy environments or overlapping sounds.
4. The device of claim 1 , wherein: either the first set of positive video and audio behaviors, or the second set of negative video and audio behaviors, or both, comprise both at least one video behavior and at least one audio behavior.
This invention relates to a behavioral monitoring device designed to analyze and classify human behavior using both video and audio inputs. The device addresses the challenge of accurately detecting and distinguishing between positive and negative behaviors in real-time, which is critical for applications such as mental health monitoring, security, and human-computer interaction. The device includes a sensor system that captures video and audio data from a subject. The system processes this data to identify and categorize behaviors into two distinct sets: a first set of positive video and audio behaviors and a second set of negative video and audio behaviors. The invention ensures that at least one of these sets—or both—includes both video-based behaviors (e.g., facial expressions, body language) and audio-based behaviors (e.g., speech patterns, vocal tones). This dual-modal approach enhances accuracy by cross-referencing visual and auditory cues, reducing false positives and improving behavioral assessment reliability. The device may be used in environments where behavioral analysis is essential, such as healthcare settings, surveillance systems, or interactive applications. By integrating both video and audio data, it provides a more comprehensive and nuanced understanding of human behavior compared to single-modal systems. The invention’s ability to detect and differentiate between positive and negative behaviors in real-time makes it particularly valuable for applications requiring immediate feedback or intervention.
5. The device of claim 1 , wherein: the classifying by the second processor comprises: at least one substitution of a video behavior with an audio behavior or a substitution of an audio behavior with a video behavior, or both, prior to computation of the least difference and prior to the computation of the largest difference.
This invention relates to a device for analyzing and classifying behaviors in multimedia content, addressing the challenge of accurately identifying and distinguishing between video and audio behaviors in complex data streams. The device includes a first processor that computes a first difference between a video behavior and a reference video behavior, and a second difference between an audio behavior and a reference audio behavior. A second processor then classifies the behaviors by substituting at least one video behavior with an audio behavior, or vice versa, before calculating the least and largest differences between the behaviors. This substitution step ensures that the classification process accounts for potential mismatches or overlaps between video and audio behaviors, improving accuracy in behavior recognition. The device may also include a memory for storing reference behaviors and a display for presenting the classification results. The substitution mechanism allows the system to handle cases where behaviors are not perfectly aligned between modalities, enhancing robustness in real-world applications such as surveillance, content analysis, or human-computer interaction.
6. The device of claim 1 , wherein: the first set of positive video and audio behaviors and the second set of negative video and audio behaviors are generated using a same vivarium environment and a same animal type as the study animal type.
This invention relates to a device for studying animal behavior using controlled video and audio stimuli. The problem addressed is the need for consistent and reproducible behavioral analysis in animal studies, particularly when evaluating responses to positive and negative stimuli. The device generates two distinct sets of video and audio behaviors—a first set representing positive stimuli and a second set representing negative stimuli—both derived from the same vivarium environment and the same animal type as the study animal. This ensures that variations in behavior are attributable to the stimuli rather than environmental or species differences. The device may include sensors to capture animal responses, such as movement or vocalizations, and processing components to analyze these responses in relation to the presented stimuli. The use of identical environmental and species conditions for both positive and negative stimuli enhances the reliability of behavioral observations, reducing confounding variables. This approach is particularly useful in neuroscience, psychology, and pharmaceutical research, where precise behavioral measurements are critical for understanding animal responses to different conditions. The invention improves upon prior methods by standardizing the experimental setup, ensuring that behavioral differences are directly linked to the stimuli rather than external factors.
7. The device of claim 1 , wherein: the classified ultrasonic vocalizations comprise identification of vocalization in one of two predetermined frequency bands, wherein a range of the two predetermined frequency bands are responsive to the study animal type.
This invention relates to a device for analyzing ultrasonic vocalizations from study animals, addressing the challenge of accurately classifying and identifying these high-frequency sounds, which are often beyond human hearing range. The device is designed to process and categorize ultrasonic vocalizations into two distinct frequency bands, where each band corresponds to specific animal types. The frequency ranges of these bands are selected based on the known vocalization patterns of the animals being studied, ensuring accurate identification. The device likely includes sensors or microphones capable of detecting ultrasonic frequencies, signal processing components to filter and analyze the incoming sounds, and classification algorithms to determine which of the two frequency bands each vocalization falls into. This classification helps researchers distinguish between different types of vocalizations, such as distress calls, mating calls, or social interactions, based on the animal species being observed. The system may also include data storage and output mechanisms to record and display the results for further analysis. By tailoring the frequency bands to the study animal type, the device improves the precision of vocalization identification, making it a valuable tool for ethological and behavioral research.
8. The device of claim 1 , wherein: at least a subset of audio behaviors comprise classified non-vocalization sounds.
The invention relates to audio processing systems designed to analyze and classify sounds, particularly focusing on distinguishing between vocalizations and non-vocalization sounds. The core technology involves a device that processes audio inputs to identify and categorize different audio behaviors, with an emphasis on recognizing non-vocalization sounds such as environmental noises, mechanical sounds, or other non-speech audio events. The system may use machine learning or pattern recognition techniques to classify these sounds, enabling applications in surveillance, animal behavior monitoring, industrial equipment diagnostics, or smart home systems. By isolating and analyzing non-vocalization sounds, the device can improve noise filtering, event detection, or contextual awareness in audio-based applications. The classification of non-vocalization sounds allows the system to differentiate between relevant and irrelevant audio signals, enhancing accuracy in scenarios where vocalizations are not the primary focus. This capability is particularly useful in environments where distinguishing between speech, animal sounds, and background noise is critical for accurate data interpretation or automated decision-making. The device may integrate with other audio processing modules to provide a comprehensive analysis of the acoustic environment.
9. The device of claim 1 , wherein: the plurality of cages in the vivarium are free of electronic penetrations and are home cages of their respective animals.
This invention relates to a vivarium system for housing animals, particularly designed to maintain controlled environments while minimizing disruptions. The system includes multiple cages, each serving as a home cage for individual animals, with no electronic penetrations to ensure a stable and interference-free environment. The cages are part of a larger vivarium structure that provides automated monitoring and control of environmental conditions such as temperature, humidity, and lighting without requiring direct electronic connections to the cages themselves. This design prevents external disturbances that could affect animal behavior or health, making it suitable for research applications where precise environmental control is critical. The system may also include sensors and actuators integrated into the vivarium framework rather than within the cages, allowing for remote monitoring and adjustments while maintaining the integrity of the animals' living spaces. The absence of electronic penetrations in the cages ensures a clean, uncontaminated environment, reducing the risk of infections or other complications. The overall design aims to enhance animal welfare while enabling accurate and reliable experimental conditions.
10. The device of claim 1 , wherein: the at least one ultrasonic audio sensor is mechanically independent of the proximal cage such that the at least one ultrasonic audio sensor or the proximal cage is replaceable without mechanically moving the proximal cage or the at least one ultrasonic audio sensor, respectively.
This invention relates to a medical device with an ultrasonic audio sensor system designed for minimally invasive procedures. The device addresses the challenge of integrating sensors into flexible or movable components while ensuring modularity and ease of maintenance. The core structure includes a proximal cage, which is part of a larger device, and at least one ultrasonic audio sensor. The sensor is mechanically independent of the proximal cage, allowing either component to be replaced without disturbing the other. This independence simplifies repairs, upgrades, or adjustments, as the sensor or cage can be swapped individually without requiring disassembly of the entire system. The design ensures that the sensor remains functional and properly aligned during use, even if the cage is repositioned or replaced. This modular approach enhances flexibility in clinical settings, where quick adjustments or part replacements may be necessary. The invention is particularly useful in devices requiring precise acoustic monitoring, such as endoscopes or surgical tools, where sensor reliability and ease of maintenance are critical.
11. The device of claim 1 , wherein: the device is free of manually observed behavior of the study animals, and free of manually communicated behavior of the study animals, and free of manual classifying of sets of behaviors.
This invention relates to automated animal behavior monitoring systems, specifically for studying animals without human intervention. The system eliminates the need for manual observation, communication, or classification of animal behaviors, reducing human bias and increasing efficiency. The device includes sensors to detect and record animal movements, vocalizations, or other behaviors, and processes this data using algorithms to identify and categorize behaviors automatically. Unlike traditional methods that rely on human observers to note and classify behaviors, this system operates independently, ensuring consistent and objective data collection. The technology is particularly useful in research settings where unbiased, large-scale behavioral analysis is required, such as in neuroscience, ethology, or drug development studies. By removing manual steps, the system improves accuracy, reduces labor costs, and enables continuous monitoring over extended periods. The device may also integrate with other data sources, such as environmental sensors, to correlate behaviors with external factors like temperature or lighting conditions. The automated classification ensures reproducibility and scalability, making it suitable for studies involving multiple animals or long-term behavioral tracking.
12. The device of claim 1 , wherein: the detection and automatic communication of one or more audio and video behaviors is continuous.
This invention relates to a device for continuously detecting and automatically communicating audio and video behaviors. The device operates within a surveillance or monitoring system, addressing the need for real-time analysis of audio and video data to identify specific behaviors or events. The system captures audio and video inputs from one or more sources, processes the data to detect predefined behaviors, and automatically transmits alerts or notifications when such behaviors are identified. The continuous operation ensures that the device monitors inputs without interruption, providing ongoing detection and communication of relevant events. The device may include sensors, processing units, and communication modules to facilitate this functionality. The continuous detection and communication aspect distinguishes it from systems that operate intermittently or require manual intervention. This technology is applicable in security, healthcare, industrial monitoring, and other fields where real-time behavior analysis is critical. The invention improves situational awareness and response times by eliminating delays in detection and reporting.
13. The device of claim 1 , wherein: the at least one video sensor is mechanically independent of the proximal cage such that the at least one video sensor or the proximal cage are configurable to be replaced without mechanically moving the proximal cage or the at least one video sensor, respectively.
This invention relates to a medical device, specifically a catheter system with a proximal cage and at least one video sensor. The device addresses the challenge of maintaining flexibility and modularity in catheter-based imaging systems, where components like video sensors or structural elements may need replacement or adjustment without disrupting the entire system. The proximal cage, which provides structural support, is mechanically independent of the video sensor(s). This independence allows either the video sensor or the proximal cage to be replaced or reconfigured without requiring movement or modification of the other component. The design ensures that adjustments or replacements can be made without compromising the integrity or functionality of the remaining parts, improving usability and maintenance in medical procedures. The modular approach also facilitates upgrades or repairs, as individual components can be swapped without extensive disassembly. This feature is particularly valuable in minimally invasive procedures where precision and efficiency are critical. The invention enhances the adaptability of catheter-based systems, ensuring reliable performance while accommodating different procedural needs.
14. A device for automatically classifying animal behaviors comprising: a study animal type; a vivarium comprising a set of study animals, of the study animal type, in a plurality of cages; a non-transitory first memory comprising a first set of positive video and audio behaviors; a non-transitory second memory comprising a second set of negative video and audio behaviors; at least one ultrasonic audio sensor proximal to an each cage in the plurality of cages; at least one video camera proximal to the each cage in the plurality of cages; wherein at least one ultrasonic sensor and at least one video sensor detect automatically and communicate first communicated behaviors comprising one or more audio and video behaviors, from the at least one cage in the plurality of cages, respectively; a first processor adapted to identify a first selected set of behaviors derived from the first communicated behaviors, wherein each behavior in the first selected set of behaviors is consistent with one or both at least one behavior in the first set of positive video and audio behaviors; or at least one behavior in the second set of negative video and audio behaviors; a second processor adapted to classify the first selected set of behaviors responsive to at least both of: (a) a least difference between the first selected set of behaviors and the first set of positive video and audio behaviors, and (b) a largest difference between the first selected set of behaviors and the second set of negative video and audio behaviors; wherein the first and second processors are configurable to operate as a the same processor; wherein each of the automatically classified animal behaviors is quantified; wherein at least a subset of the automatically classified animal behaviors by the device is quantified; wherein a study using the set of study animals is terminated, responsive to the classified ultrasonic vocalizations.
This invention relates to an automated system for classifying animal behaviors in research settings, particularly for monitoring study animals in vivariums. The system addresses the challenge of manually observing and categorizing animal behaviors, which is time-consuming and prone to human error. It automates the detection and classification of behaviors using video and ultrasonic audio sensors placed near each cage in a vivarium containing multiple animals of a specified type. The system includes two memory modules: one storing predefined positive behaviors (e.g., normal or desirable activities) and another storing negative behaviors (e.g., distress or abnormal activities). Sensors capture audio and video data from the cages, which is processed by a first processor to identify behaviors matching those in the positive or negative datasets. A second processor then classifies these behaviors based on the smallest difference from positive behaviors and the largest difference from negative behaviors. The processors can be configured to operate as a single unit. The system quantifies the classified behaviors, allowing researchers to track and analyze them. The study can be automatically terminated if certain classified behaviors, such as distress vocalizations, are detected. This automation improves efficiency and consistency in behavioral research.
15. A method for automatically classifying animal behaviors comprising: a study animal type; a vivarium comprising a set of study animals, of the study animal type, in a plurality of cages; a non-transitory first memory comprising a first set of positive video and audio behaviors; a non-transitory second memory comprising a second set of negative video and audio behaviors; at least one ultrasonic audio sensor proximal to an each cage in the plurality of cages; at least one video camera proximal to the each cage in the plurality of cages; wherein the method comprises the steps: communicating automatically first communicated behaviors detected by at least one ultrasonic sensor and at least one video sensor wherein the first communicated behaviors comprise one or more audio and video behaviors, from the at least one cage in the plurality of cages; identifying by a first processor a first selected set of behaviors derived from the first communicated behaviors, wherein each behavior in the first selected set of behaviors is consistent with one or both of at least one behavior in the first set of positive video and audio behaviors; or at least one behavior in the second set of negative video and audio behaviors; classifying by a second processor the first selected set of behaviors responsive to at least both of: (a) a least difference between the first selected set of behaviors and the first set of positive video and audio behaviors, and (b) a largest difference between the first selected set of behaviors and the second set of negative video and audio behaviors; wherein the first and second processors are configurable to operate as a same processor; quantifying by the method each of the automatically classified animal behaviors; accepting as dispositive animal behavior of at least a subset of the automatically classified animal behaviors comprising classified ultrasonic vocalization.
This invention relates to automated classification of animal behaviors in a vivarium setting, addressing challenges in accurately and efficiently monitoring animal welfare, research behaviors, or experimental conditions. The system involves a vivarium with multiple cages containing study animals of a specified type. Each cage is equipped with at least one ultrasonic audio sensor and one video camera to capture audio and visual behaviors. The system uses two memory stores: one containing positive reference behaviors (desired or normal activities) and another containing negative reference behaviors (undesired or abnormal activities). The method involves automatically detecting and communicating behaviors from the sensors, then processing these behaviors to identify a subset that matches either positive or negative reference behaviors. A processor classifies these behaviors based on the smallest difference to positive references and the largest difference to negative references, ensuring accurate categorization. The system can quantify classified behaviors, with ultrasonic vocalizations being a key dispositive factor. The processors may operate as a single unit. This approach enables real-time, automated monitoring of animal behaviors, improving research efficiency and animal welfare assessment.
16. A system for automatically classifying animal behaviors comprising: a study animal type; a vivarium comprising a set of study animals, of the study animal type, in a plurality of cages; a non-transitory first memory comprising a first set of positive video and audio behaviors; a non-transitory second memory comprising a second set of negative video and audio behaviors; at least one ultrasonic audio sensor proximal to an each cage in the plurality of cages; at least one video camera proximal to the each cage in the plurality of cages; wherein at least one ultrasonic sensor and at least one video sensor detect and automatically communicate first communicated behaviors comprising one or more audio and video behaviors, from the at least one cage in the plurality of cages, respectively; a first processor adapted to identify a first selected set of behaviors derived from the first communicated behaviors, wherein each behavior in the first selected set of behaviors is consistent with one or both of at least one behavior in the first set of positive video and audio behaviors; or at least one behavior in the second set of negative video and audio behaviors; a second processor adapted to classify the first selected set of behaviors responsive to at least both of: (a) a least difference between the first selected set of behaviors and the first set of positive video and audio behaviors and (b) a largest difference between the first selected set of behaviors and the second set of negative video and audio behaviors; wherein the first and second processors are configurable to operate as a same processor; wherein each of the automatically classified animal behaviors by the system is quantified; wherein the at least a subset of the automatically classified animal behaviors comprising classified ultrasonic vocalization is then used as accepted dispositive animal behavior.
The system automatically classifies animal behaviors in a vivarium setting, addressing the challenge of manually monitoring and analyzing animal behavior in research environments. The system includes a vivarium with multiple cages housing study animals of a specific type. Each cage is equipped with at least one ultrasonic audio sensor and one video camera to detect and record audio and video behaviors from the animals. These sensors communicate the detected behaviors to a processing system. The system uses two memory stores: one containing a set of positive video and audio behaviors (desired or normal behaviors) and another containing a set of negative video and audio behaviors (undesired or abnormal behaviors). A first processor identifies behaviors from the detected data that match either the positive or negative behavior sets. A second processor then classifies these behaviors based on the smallest difference between the detected behaviors and the positive behaviors, and the largest difference between the detected behaviors and the negative behaviors. The processors can be configured to operate as a single unit. The system quantifies the classified behaviors, and a subset of these, particularly ultrasonic vocalizations, is used as definitive evidence of animal behavior. This automated approach improves efficiency and accuracy in behavioral research, reducing reliance on manual observation.
Unknown
November 3, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.